Abstract
In this paper, we propose a subMarkov random walk (subRW) with the label prior with added auxiliary nodes for seeded image segmentation. We unify the proposed subRW and the other popular random walk algorithms. This unifying view can transfer the intrinsic findings between different random walk algorithms, and offer the new ideas for designing the novel random walk algorithms by changing the auxiliary nodes. According to the second benefit, we design a subRW algorithm with label prior to solve the segmentation problem of objects with thin and elongated parts. The experimental results on natural images with twigs demonstrate that our algorithm achieves better performance than the previous random walk algorithms.
This work was supported in part by the National Basic Research Program of China (973 Program) (No. 2013CB328805), the Key Program of NSFC-Guangdong Union Foundation (No. U1035004), the National Natural Science Foundation of China (No. 61272359), and the Program for New Century Excellent Talents in University (NCET-11-0789). Beijing Higher Education Young Elite Teacher Project. Specialized Fund for Joint Building Program of Beijing Municipal Education Commission.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Calinon, S., Guenter, F., Billard, A.: On learning, representing and generalizing a task in a humanoid robot. IEEE Trans. on Systems, Man and Cybernetics, Part B 37(2), 286–298 (2007)
Couprie, C., Grady, L., Najman, L., Talbot, H.: Power watershed: A unifying graph-based optimization framework. IEEE Trans. on Pattern Analysis and Machine Intelligence 33(7), 1384–1399 (2011)
Grady, L.: Multilabel random walker image segmentation using prior models. In: IEEE CVPR, pp. 763–770 (2005)
Grady, L.: Random walks for image segmentation. IEEE Trans. on Pattern Analysis and Machine Intelligence 28(11), 1768–1783 (2006)
Grady, L., Funka-Lea, G.: Multi-label image segmentation for medical applications based on graph-theoretic electrical potentials. In: Sonka, M., Kakadiaris, I.A., Kybic, J. (eds.) CVAMIA/MMBIA 2004. LNCS, vol. 3117, pp. 230–245. Springer, Heidelberg (2004)
Jegelka, S., Bilmes, J.: Submodularity beyond submodular energies: coupling edges in graph cuts. In: IEEE CVPR, pp. 1897–1904 (2011)
Kim, T.H., Lee, K.M., Lee, S.U.: Generative image segmentation using random walks with restart. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 264–275. Springer, Heidelberg (2008)
Kohli, P., Osokin, A., Jegelka, S.: A principled deep random field model for image segmentation. In: IEEE CVPR, pp. 1971–1978 (2013)
Lawler, G.F., Limic, V.: Random walk: a modern introduction. Cambridge University Press (2010)
Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: IEEE ICCV, vol. 2, pp. 416–423 (2001)
Peng, J., Shen, J., Jia, Y., Li, X.: Saliency cut in stereo images. In: IEEE ICCVW, pp. 22–28 (2013)
Qiu, H., Hancock, E.R.: Clustering and embedding using commute times. IEEE Trans. on Pattern Analysis and Machine Intelligence 29(11), 1873–1890 (2007)
Shen, J., Du, Y., Wang, W., Li, X.: Lazy random walks for superpixel segmentation. IEEE Trans. on Image Processing 23(4), 1451–1462 (2014)
Sinop, A.K., Grady, L.: A seeded image segmentation framework unifying graph cuts and random walker which yields a new algorithm. In: IEEE ICCV, pp. 1–8 (2007)
Vicente, S., Kolmogorov, V., Rother, C.: Graph cut based image segmentation with connectivity priors. In: IEEE CVPR, pp. 1–8 (2008)
Wu, X.M., Li, Z., So, A.M., Wright, J., Chang, S.F.: Learning with partially absorbing random walks. In: NIPS, pp. 3077–3085 (2012)
Zhu, X., Nejdl, W., Georgescu, M.: An adaptive teleportation random walk model for learning social tag relevance. In: ACM SIGIR, pp. 223–232 (2014)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Dong, X., Shen, J., Van Gool, L. (2015). Segmentation Using SubMarkov Random Walk. In: Tai, XC., Bae, E., Chan, T.F., Lysaker, M. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 2015. Lecture Notes in Computer Science, vol 8932. Springer, Cham. https://doi.org/10.1007/978-3-319-14612-6_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-14612-6_18
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-14611-9
Online ISBN: 978-3-319-14612-6
eBook Packages: Computer ScienceComputer Science (R0)